The Next Generation Information Retrieval group looks at search and information retrieval in a world impacted by Linux and Google where open source and open standards are becoming a dominant paradigm for internet services, and information retrieval is viewed as a key function in productive internet use. The group uses probabilistic and information-theoretic methods to model information retrieval, and is committed to open source software development. The group also believes distributed, semantic-based and multilingual methods will have a central role in the future of information retrieval.

The work is done in the following research projects:

PROSE - Scalable Probabilistic Methods for the Next Generation Search Engine
PROSE uses advances in probabilistic methods to develop a search engine kernel using for instance probabilistic models of queries and text and topics. Prose is funded by the Academy of Finland.
SIB - Search-Ina-Box
SIB will research and develop software for search, which employs hidden language models and probabilistic query evaluation models and tightly integrates personalization with search. This will allow users to search by example, matching via topic and synonym. Intranets are a practical arena for personalized, semantic-based search. SIB is funded by the Fenix Research Programme of the National Technology Agency of Finland.
ALVIS - Superpeer Semantice Search Engine
Next generation search methods can make semantic-based, personalized, peer-to-peer search possible. It will produce fine-grained topic and genre classifications and synonyms automatically. The core elements of the Search Engine will be offered under GNU General Public License, which works towards making search an integral part of the web infrastructure as supported by the Open Source Search initiative. Thus the classified web data becomes available for businesses and the public sector. Alvis is funded by EU's Sixth Framework Programme for Research and Technological Development.